Jonne Pohjankukka
Doctor of Philosophy
jjepoh@utu.fi ORCID identifier: https://orcid.org/0000-0002-5808-2577 |
Computer science, data analysis, machine learning, statistical methods
Data-analytics, Algorithms and Computational Intelligent (ACI) research group
Data scientist specialized in machine learning and computer vision. My background is from research and development work via AI solutions, which I have worked on both in the public and private sectors. My main job responsibilities during the last years have revolved around analytical problem solving via machine learning and statistical methods, project management, producing intelligent cloud-based software solutions for institutions and client companies. My work also involves coordination and teaching of machine learning experts and methods, organizing seminars and public presentations.
My Ph.D. studies were focused on the development and application of machine learning techniques for open remotely sensed data sets. I have a passionate interest in all the sciences and technologies related to artificial intelligence, and I actively increase my frame reference on these subjects like the latest software, algorithm and theoretical solutions.
- Top skills -
◼️ Data analysis
◼️ Machine learning
◼️ Computer vision
◼️ Statistical modeling
◼️ Mathematics / Optimization
◼️ Software engineering
◼️ Signal / Digital image processing
◼️ Model validation
My research is focused on the development and application of machine learning techniques for open remotely sensed data sets and deep learning solutions in sensor fusion domains.
I work as an assistant lecturer on courses related to the application and validation of machine learning methods with real-world data sets. My interest areas include deep learning, Gaussian processes and Bayesian methods generally.
- Peatland pixel-level classification via multispectral, multiresolution and multisensor data using convolutional neural network (2025)
- Ecological Informatics
(A1 Refereed original research article in a scientific journal) - Multistream Convolutional Neural Network Fusion for Pixel-wise Classification of Peatland (2023) 2023 26th International Conference on Information Fusion (FUSION) Farahnakian Fahimeh, Zelioli Luca, Pitkänen Timo, Pohjankukka Jonne, Middleton Maarit, Tuominen Sakari, Nevalainen Paavo, Heikkonen Jukka
(A4 Refereed article in a conference publication ) - Bayesian Approach for Optimizing Forest Inventory Survey Sampling with Remote Sensing Data (2022)
- Forests
(A1 Refereed original research article in a scientific journal) - Towards dynamic forest trafficability prediction using open spatial data, hydrological modelling and sensor technology (2020)
- Forestry
(A1 Refereed original research article in a scientific journal) - Radiomics and machine learning of multisequence multiparametric prostate MRI: Towards improved non-invasive prostate cancer characterization (2019)
- PLoS ONE
(A1 Refereed original research article in a scientific journal) - The spatial leave-pair-out cross-validation method for reliable AUC estimation of spatial classifiers (2019)
- Data Mining and Knowledge Discovery
(A1 Refereed original research article in a scientific journal) - Comparison of estimators and feature selection procedures in forest inventory based on airborne laser scanning and digital aerial imagery (2018)
- Scandinavian Journal of Forest Research
(A1 Refereed original research article in a scientific journal) - Effect of homogenised and pasteurised versus native cows' milk on gastrointestinal symptoms, intestinal pressure and postprandial lipid metabolism (2018)
- International Dairy Journal
(A1 Refereed original research article in a scientific journal) - Machine Learning Approaches for Natural Resource Data (2018) Pohjankukka Jonne
(G5 Article dissertation ) - Estimating the prediction performance of spatial models via spatial k-fold cross validation (2017)
- International Journal of Geographical Information Science
(A1 Refereed original research article in a scientific journal)



